Resource Allocation in Edge and Cloud Integrated Environment Using Machine Learning Algorithms

Edge and Cloud computing are the significant entities in the present technological era with multiple usages of resources. Resource allocation is the process in which the resources such as hardware, software and network devices are allocated strategically to make the best and most efficient use of the resources. The resources provided to the users with less management and optimal resource allocation mechanism. Traditionally, resource allocation problems have been solved online utilizing real-time data on computational resources such as the processing elements, main and secondary memory. These problems are generally convex, and finding solutions is challenging. Resource allocation based on First-In-First-Out, Last-In-First-Out, Round Robin and Greedy methods are commonly used. A machine learning based resource allocation strategy is proposed to improve the system performance. The main goal is to find the optimal resource allocation strategy using machine learning algorithms such as DBSCAN, BIRCH, DecisionTree, KNN and KMEANS. The experimental results indicate that the resources are assigned to the users in minimal time compared to Greedy and other baseline algorithms.